Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3661 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.8962. Min Act: -0.0001

Data Index: 782784 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.7561. Min Act: -0.0001

Data Index: 281351 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.8658. Min Act: -0.0001

Data Index: 968032 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.6894. Min Act: -0.0001

Data Index: 510642 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.6676. Min Act: -0.0001

Data Index: 730140 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.7180. Min Act: -0.0001

Data Index: 57419 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.6709. Min Act: -0.0001

Data Index: 18962 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.7088. Min Act: -0.0001

Data Index: 1336467 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.6765. Min Act: -0.0001

Data Index: 490639 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.6612. Min Act: -0.0001

Data Index: 14294 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.6974. Min Act: -0.0001

Data Index: 681780 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.6122. Min Act: -0.0001

Data Index: 1328716 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.6851. Min Act: -0.0001

Data Index: 578129 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.6782. Min Act: -0.0001

Data Index: 658936 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.7111. Min Act: -0.0001

Data Index: 354332 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.5580. Min Act: -0.0001

Data Index: 1185037 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.6560. Min Act: -0.0001

Data Index: 1190886 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.6926. Min Act: -0.0001

Data Index: 55065 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.6060. Min Act: -0.0001

Data Index: 849759 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.6314. Min Act: -0.0001

Data Index: 36354 (C4 (Web Text))

Max Activating Token Index: 507